Error "Arena size is too small for all buffers" while inferencing audio project on XIAO ESP32-S3.

[salmanfaris]

Hi, I was trying to inference an audio KWS project on XIAO ESP-S3 with Sense HAT. The device was working fine on the previous audio project, only facing issues with this particular project. Thanks in Advance.

ERR: Failed to run classifier (-3)
Arena size is too small for all buffers. Needed 15280 but only 12160 was available.
AllocateTensors() failed
ERR: Failed to run classifier (-3)
Edge Impulse Inferencing Demo
Inferencing settings:
Interval: 0.062500 ms.
Frame size: 16000
Sample length: 1000 ms.
No. of classes: 2

[kowshik1729]

@salmanfaris

This seems to be a typical Dynamic memory allocation done through your software stack. I've seen similar error while implementing OpenCV on MCU's.

Try freeing unused objects from your application.

[salmanfaris]

Thanks for the insights @kowshik1729 .

When I was checking the edgeImpulse memory profiler, it only mentioned 19.1K RAM and I don't have any additional application running along with the inference program. It looks like something is wrong in the compilation.

I will try to check the memory status as you mentioned and get back, Thanks